Title: Side-path FPN-based multi-scale object detection

Authors: Weixian Wan; Xiangfeng Luo; Liyan Ma; Shaorong Xie

Addresses: School of Computer Engineering and Science, Shanghai University, Shanghai, China ' School of Computer Engineering and Science, Shanghai University, Shanghai, China ' School of Computer Engineering and Science, Shanghai University, Shanghai, China ' School of Computer Engineering and Science, Shanghai University, Shanghai, China

Abstract: Multi-scale object detection faces the problem of how to obtain distinguishable features. Feature pyramid network (FPN) is the most typical work to construct a feature pyramid to obtain multi-scale features, and is beneficial for multi-scale object detection tasks to improve the mean average precision (mAP) of the detectors. However, due to the lack of feature selection to eliminate redundant information, FPN cannot make full use of multi-scale features. In this paper, side-path FPN is proposed to address this problem. Side-path FPN contains two components: feature alignment and feature fusion. The feature alignment component uses the best operator to extract features. The feature fusion component can enhance features that are helpful for detection and reduce redundant information. With ResNet-50 as the backbone, compared to the original FPN, side-path FPN improves mAP by 1.8 points on the VOC2007 test dataset and 1.0 point on the COCO 2017 test dataset with MS COCO metrics.

Keywords: object detection; multiple scale; feature selection.

DOI: 10.1504/IJCSE.2022.120787

International Journal of Computational Science and Engineering, 2022 Vol.25 No.1, pp.44 - 51

Received: 29 Jan 2021
Accepted: 16 Mar 2021
Published online: 08 Feb 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article